SkillsAdd

necmttn/ax

ship-checklist

Definition-of-done checklist for shipping a new write, signal, table, edge, or query to the ax graph. Use when adding a SurrealDB table/edge/field, an ingest derive-stage, a new analytic query, or any new ax capability - before opening the PR. Ensures every write gets an on-demand read AND a proactive (agent-facing) read AND docs/distribution, not just the write. Triggers on "ship", "new signal", "new table/edge", "new lens/query", "wire this up", "is this done", or finishing an ax feature bran…

First seen Jun 17, 2026

Installation

$ npx skills add necmttn/ax --skill ship-checklist
View on skills.sh ↗ GitHub repository ↗

Summary

  • Definition-of-done checklist for shipping a new write, signal, table, edge, or query to the ax graph.
  • Use when adding a SurrealDB table/edge/field, an ingest derive-stage, a new analytic query, or any new ax capability - before opening the PR.
  • Ensures every write gets an on-demand read AND a proactive (agent-facing) read AND docs/distribution, not just the write.
  • Triggers on "ship", "new signal", "new table/edge", "new lens/query", "wire this up", "is this done", or finishing an ax feature branch.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

find-skills Same topic
vercel-labs/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "fi…

3.3M installs
agent-browser Same topic
vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, includ…

810.4K installs
vercel-react-best-practices Same topic
vercel-labs/agent-skills 697.8K installs
web-design-guidelines Same topic
vercel-labs/agent-skills

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "chec…

617.3K installs
microsoft-foundry Same topic
microsoft/azure-skills

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and …

576.5K installs
azure-prepare Same topic
microsoft/azure-skills

Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Te…

568.3K installs

Also in this package

Other skills from necmttn/ax.

npx skills add necmttn/ax
retro 117 setup 112 ax-extract-workflow 111 retro-meta 110 release-announcement 106 ax-repo 105 ax-narrate 98 efficient-dispatch 97

Browse all from necmttn/ax

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 105
License LICENSE
Default branch main
Open issues 35
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

Declared agents claude-code

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,489 B
  • docs SUMMARY.md 524 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 89 installs

SKILL.md

ship-checklist - every write needs a read path an agent can find

The recurring miss in ax: we ship the write + an on-demand CLI read, and skip the proactive / agent-facing read. A signal only visible on a manual CLI run is invisible to the self-improvement loop. ax's whole thesis is that agents discover and act on signals - so a new write is not done until an agent can find it without being told.

Organizing rule: every write needs (B) an on-demand read AND (C) a proactive read AND an agent-facing surface (MCP/skill). Most features do A+B and stop.

Run this before opening the PR. Skipping a row is fine - but say so in the PR and why, don't skip silently.

A. Write

  • Schema in schema.surql + registered in SCHEMA_TABLES (CI mirror guard)
  • Ingest idempotent + incremental (since-aware) + deref-free denormalization for reads (no record derefs inside aggregates - they hang prod)
  • Backfill: does history get the signal, or only new data? Note "dark until re-ingest" if so
  • Stage deps = every producer of the input table

B. Read - on-demand

  • CLI: a command or a facet on an existing one (consistent family)
  • --json envelope for scripting
  • Dashboard/studio surface (if visual)

C. Read - proactive (the usually-missed half)

  • MCP tool so an agent can query it in-context (apps/axctl/src/mcp/tools.ts)
  • ax improve recommend generator - mint a proposal when the signal crosses a threshold (agent gets the suggestion unprompted)
  • ax insights / dashboard next-actions wiring (if it implies an action)
  • dojo agenda item (if the overnight loop should act on it)
  • Skill: a cognitive pattern teaching an agent to act on the signal (e.g. the ln skill routes visual judgment to subagents off ax cost images)

D. Documentation

  • CLAUDE.md command/section docs (there is a docs gate for new subcommands)
  • llms.txt / site docs / README, if user-facing
  • CHANGELOG + release notes (release-please)
  • Spec in docs/superpowers/specs/ for non-trivial features

E. Onboarding / distribution

  • Onboarding prompt (@ax/onboarding-prompt) - should a day-1 user/agent know it exists?
  • Marketing coverage (site page / blog / X), if a user-facing capability
  • /api/version capability flag, if relevant

F. Verify (evidence, not assertion)

  • Tests: unit on pure helpers + schema-mirror guard + CLI command-list test
  • Live-verified against the real DB - paste the actual output in the PR
  • "Dark until data" honesty: state if it needs backfill/telemetry to light up

How to use

Create a TodoWrite item per relevant row, or paste the A-F headers into the PR body as a checked list. The point is the C section - if a new signal has no MCP tool, no improve generator, and no skill, an agent will never surface it on its own, and the feature is half-built no matter how clean the write is.